Forest-cover monitoring based on high resolution remote sensing image

DOI

10.2991/icitmi-15.2015.93How to use a DOI?

Keywords

High resolution; Multi-scale segmentation; KNN; Rules-based; Forest-cover monitoring

Abstract

The article put forward a method on forest-cover monitoring based on high resolution remote sensing data of adjacent two year and existing vector data of forest sub-compartment. With the GF- 2 remote sensing image and Rapid-Eye images as the data sources, multi-scale segmentation under the forest land boundary control was conducted, and object of deforestation samples were selected. The object-oriented method of KNN and rules-based were used to classify the image and extract the patches of deforestation. Then we get the deforestation vector diagram of early and later periods. The deforestation patches of two periods were compared and analyzed to achieve the deforestation and recovering vector diagram in a year. Finally, the paper proved the feasibility of the method in forest-cover monitoring application by accuracy analysis.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Jiajie Cui
AU  - Shiming Li
PY  - 2015/10
DA  - 2015/10
TI  - Forest-cover monitoring based on high resolution remote sensing image
BT  - Proceedings of the 4th International Conference on Information Technology and Management Innovation
PB  - Atlantis Press
SP  - 569
EP  - 575
SN  - 2352-538X
UR  - https://doi.org/10.2991/icitmi-15.2015.93
DO  - 10.2991/icitmi-15.2015.93
ID  - Cui2015/10
ER  -